Articulated and Restricted Motion Subspaces and Their Signatures

IEEE Trans. Pattern Anal. Mach. Intell.

Demiris

2018

Abstract-In this paper, we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view 2D image sequence. In contrast to prior motion-based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology via a successive iterative merging strategy. The iterative merge process is guided by a density weighted skeleton map which is generated from a novel object boundary generation method from sparse 2D feature points. Our main contributions can be summarised as follows: (i) An unsupervised complex articulated kinematic structure estimation method that combines motion segments with skeleton information. (ii) An iterative fine-to-coarse merging strategy for adaptive motion segmentation and structural topology embedding. (iii) A skeleton estimation method based on a novel silhouette boundary generation from sparse feature points using an adaptive model selection method. (iv) A new highly articulated object dataset with ground truth annotation. We have verified the effectiveness of our proposed method in terms of computational time and estimation accuracy through rigorous experiments with multiple datasets. Our experiments show that the proposed method outperforms state-of-the-art methods both quantitatively and qualitatively.Index Terms-Highly articulated kinematic structure estimation, adaptive motion segmentation, density weighted silhouette generation from sparse points, adaptive kernel selection.

Section: Related Workmentioning

confidence: 99%

“…folding, rotation, and translation) of relatively simple articulations [6], [7]. They have also been used to build kinematic chains in order to 3D reconstruct articulated objects [6], [8].…”

Section: Introductionmentioning

confidence: 99%

Highly Articulated Kinematic Structure Estimation Combining Motion and Skeleton Information

IEEE Trans. Pattern Anal. Mach. Intell.

Demiris

2018

“…This is used for the discovery of behaviours such as walking and running, rather than matching of rigid segments as in our case. Jacquet et al [46] presented a relative transformation analysis method based on linear subspaces, but they focused on detecting the type of articulated motion between two restricted motion parts.…”

Section: Related Workmentioning

confidence: 99%

Learning Kinematic Structure Correspondences Using Multi-Order Similarities

IEEE Trans. Pattern Anal. Mach. Intell.

Fischer

Petit

et al. 2018

Abstract-In this paper, we present a novel framework for finding the kinematic structure correspondences between two articulated objects in videos via hypergraph matching. In contrast to appearance and graph alignment based matching methods, which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Thus our method allows matching the structure of objects which have similar topologies or motions, or a combination of the two. Our main contributions can be summarised as follows: (i) casting the kinematic structure correspondence problem into a hypergraph matching problem by incorporating multi-order similarities with normalising weights, (ii) introducing a structural topology similarity measure by aggregating topology constrained subgraph isomorphisms, (iii) measuring kinematic correlations between pairwise nodes, and (iv) proposing a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on synthetic and real data, outperforming various other state of the art methods. Our method is not limited to a specific application nor sensor, and can be used as building block in applications such as action recognition, human motion retargeting to robots, and articulated object manipulation amongst others.

“…Recently, graph structure information based alignment methods such as NETAL [25] and MAGNA++ [37] have been presented, which do not rely on node similarities. Motion description methods: Jacquet et al [15] presented a relative transformation analysis method based on linear subspaces, but they focused on detecting the type of articulated motion between two restricted motion parts. Various metrics for 3D rotations, which can be used to describe motions, have been reviewed in [14].…”

Section: Related Workmentioning

confidence: 99%

Kinematic Structure Correspondences via Hypergraph Matching

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Fischer

Petit

et al. 2016

In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching. In contrast to prior appearance and graph alignment based matching methods which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Our main contributions can be summarised as follows: (i) casting the kinematic structure correspondence problem into a hypergraph matching problem, incorporating multi-order similarities with normalising weights, (ii) a structural topology similarity measure by a new topology constrained subgraph isomorphism aggregation, (iii) a kinematic correlation measure between pairwise nodes, and (iv) a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on complex articulated synthetic and real data.